Back to corpus
architecturetechnical paper candidatescore 40

System Overview Diagram

```mermaid flowchart TB subgraph CC [Computational Choreography - The Discipline] subgraph TOS [TrajectoryOS - Long Horizon] direction TB subgraph Memory [Memory Fabric] RAG[RAG++ Core<br/>Rust: HNSW, IRCP, 5D] CT[CognitiveTwin<br/>Python ML] Sig[Style Signature<br/>EMA Learning] end subgraph Orchestration [Orchestration] Orbit[Orbit Server<br/>Axum/Rust] Sessions[Session Manager<br/>Supabase] end subgraph MCP [MCP Integration] MCPServer[MCP Server<br/>AI Tool Access] AgentSDK[Agent SDK<br/>Claude Wrapper] end end

Open full HTMLDownload HTMLCorpus JSONPaper schema

Full HTML reader

Read the full artifact

Open in new tab

Extracted abstract or opening context

| Layer | Component | Location | Input | Output | Latency | |-------|-----------|----------|-------|--------|---------| | 0 | cc-relay | `core/cc-relay` | UDP packets | MocopiStateFrame | < 50μs | | 1 | cc-collection | `core/cc-collection` | Multi-sensor | FusedSkeleton | < 100μs | | 2 | cc-window-aligner | `core/cc-window-aligner` | FusedSkeleton | MotionWindow | < 1ms | | 3 | cc-anticipation | `core/cc-anticipation` | MotionWindow | AnticipationPacket | < 2ms | | 3 | cc-gesture | `core/cc-gesture` | AnticipationPacket | GestureEvent | < 500μs | | 3.5 | dell | `core/cc-echelon/crates/dell` | Limb data | DELLState | < 500μs | | 4 | cc-brain | `core/cc-echelon/crates/cc-brain` | All semantic | LatentState, Lexicon | < 1ms | | 5-7 | cc-conductor | `core/cc-echelon/crates/cc-conductor` | Lexicon | Actions | < 1ms | | Type | Description | Dims | Schema | |------|-------------|------|--------| | `MocopiStateFrame` | Raw skeleton frame | 27 bones × 7 floats | 1.0.0 | | `FusedSkeleton` | Fused multi-sensor | 14 limbs × 13 state | 1.0.0 | | `MotionWindow` | Time-aligned frames | 50 frames @ 50Hz | 0.1.0 | | `AnticipationPacket` | Semantic signals | 7 scalars + 3 vectors | 0.1.0 | | `GestureEvent` | Classified gesture | Label + confidence | 1.0.0 | | `DELLState` | Dual-equilibrium | Fast + slow latent | 1.0.0 | | `Lexicon` | Expressive controls | 6 floats | 1.0.0 | - **Overview**: [00-OVERVIEW.md](../00-OVERVIEW.md) - **Philosophy**: [01-COMPUTATIONAL_CHOREOGRAPHY.md](../01-COMPUTATIONAL_CHOREOGRAPHY.md) - **TrajectoryOS**: [02-TRAJECTORY_OS.md](../02-TRAJECTORY_OS.md) - **Echelon**: [03-ECHELON.md](../03-ECHELON.md) - **Agent SDK**: [17-AGENT_SDK.md](../17-AGENT_SDK.md) - **Data Flow**: [data-flow.md](data-flow.md) - **Deployment**: [deployment-topology.md](deployment-topology.md)

Promotion decision

What has to happen next

Promote into a technical note or architecture paper with implementation anchors.

Why this is not always a full paper yet

Corpus pages are public-safe readers for discovered workspace artifacts. They are not automatically final papers. A corpus item becomes a polished paper only after the editable source, evidence checkpoints, references, figures, render path, and release status are attached through the paper schema.